Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    legal and privacy disclaimers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    security warnings and requests

    np_acts-logits-general · gemini-2.5-flash-lite

    sentences or fragments that look like formal legal disclaimers, warnings, or privacy/consent notices (e.g., "please be advised," "we are not responsible," "you consent to").

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.48
     الحره
    -0.47
    ⓧ
    -0.46
     nahilalakip
    -0.45
     AttributeSet
    -0.44
    Organized
    -0.44
    adpleegd
    -0.43
     Einfluß
    -0.43
     Italijani
    -0.43
    WritableDatabase
    -0.41
    POSITIVE LOGITS
    存于互联网档案馆
    0.52
     security
    0.45
     toxins
    0.43
    ſelves
    0.41
     precautions
    0.41
     Minder
    0.40
     sécurité
    0.39
     safety
    0.39
     psa
    0.39
     protest
    0.39
    Act Density 0.307%

    No Known Activations